
import numpy as np
import matplotlib.pyplot as plt
# Fixing random state for reproducibility
np.random.seed(19680801)

# fake up some data
spread = np.random.rand(50) * 100
center = np.ones(25) * 50
flier_high = np.random.rand(10) * 100 + 100
flier_low = np.random.rand(10) * -100
data = np.concatenate((spread, center, flier_high, flier_low))


fig1, ax1 = plt.subplots()
ax1.set_title('Basic Plot')
ax1.boxplot(data)

{'whiskers': [<matplotlib.lines.Line2D at 0x2bb94952610>,
  <matplotlib.lines.Line2D at 0x2bb949528e0>],
 'caps': [<matplotlib.lines.Line2D at 0x2bb94952bb0>,
  <matplotlib.lines.Line2D at 0x2bb94952e80>],
 'boxes': [<matplotlib.lines.Line2D at 0x2bb94952310>],
 'medians': [<matplotlib.lines.Line2D at 0x2bb94960190>],
 'fliers': [<matplotlib.lines.Line2D at 0x2bb94960460>],
 'means': []}


#hiển thị khoảng tin cậy xung quanh trung bình thường dựa trên trung vị +/- 1,57 x IQR / sqrt của n
fig2, ax2 = plt.subplots()
ax2.set_title('Notched boxes')
ax2.boxplot(data, notch=True)

{'whiskers': [<matplotlib.lines.Line2D at 0x2bb949c5250>,
  <matplotlib.lines.Line2D at 0x2bb949c5520>],
 'caps': [<matplotlib.lines.Line2D at 0x2bb949c57f0>,
  <matplotlib.lines.Line2D at 0x2bb949c5ac0>],
 'boxes': [<matplotlib.lines.Line2D at 0x2bb949b4f10>],
 'medians': [<matplotlib.lines.Line2D at 0x2bb949c5d90>],
 'fliers': [<matplotlib.lines.Line2D at 0x2bb949d00a0>],
 'means': []}


#Ví dụ sau vẽ biểu đồ về điểm của các sinh viên trong một lớp học. Bốn cột, 0-25, 26-50, 51-75 và 76-100 
# Add the essential library
import matplotlib.pyplot as plt
# Create the data
employee_age = [21,28,32,34,35,35,37,42,47,55]
# Create bins for histogram
bins = [20,30,40,50,60]
# Plot the histogramData Visualization Chapter 5
[ 145 ]
plt.hist(employee_age, bins, rwidth=0.6)
# Add X Label on X-axis
plt.xlabel("Employee Age")
# Add X Label on X-axis
plt.ylabel("Frequency")
# Add title to graph
plt.title("Employee Age Distribution")
# Show the plot
plt.show()


# Import required library
import seaborn as sns
# Read iris data using load_dataset() function
data = sns.load_dataset("iris")
# Find correlationData Visualization Chapter 5
[ 163 ]
cor_matrix=data.corr()
# Create heatmap
sns.heatmap(cor_matrix, annot=True)
# Show figure
plt.show()


# Create heatmap
sns.heatmap(cor_matrix, annot=True, cmap="YlGnBu")
# Show figure
plt.show()


#Số lượng sinh viên đăng ký cho các khóa học khác nhau được cung cấp tại một viện.
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_axes([0,0,1,1])
langs = ['C', 'C++', 'Java', 'Python', 'PHP']
students = [23,17,35,29,12]
ax.bar(langs,students)
plt.show()


#Đối tượng dữ liệu là một số lượng sinh viên đã đậu vào ba ngành của một trường cao đẳng kỹ thuật trong bốn năm qua.
import numpy as np
import matplotlib.pyplot as plt
data = [[30, 25, 50, 20],
[40, 23, 51, 17],
[35, 22, 45, 19]]
X = np.arange(4)
fig = plt.figure()
ax = fig.add_axes([0,0,1,1])
ax.bar(X + 0.00, data[0], color = 'b', width = 0.25)
ax.bar(X + 0.25, data[1], color = 'g', width = 0.25)
ax.bar(X + 0.50, data[2], color = 'r', width = 0.25)

<BarContainer object of 4 artists>


import matplotlib.pyplot as plt
   
Year = [1920,1930,1940,1950,1960,1970,1980,1990,2000,2010]
Unemployment_Rate = [9.8,12,8,7.2,6.9,7,6.5,6.2,5.5,6.3]
  
plt.plot(Year, Unemployment_Rate)
plt.title('Unemployment Rate Vs Year')
plt.xlabel('Year')
plt.ylabel('Unemployment Rate')
plt.show()


import matplotlib.pyplot as plt
   
Year = [1920,1930,1940,1950,1960,1970,1980,1990,2000,2010]
Unemployment_Rate = [9.8,12,8,7.2,6.9,7,6.5,6.2,5.5,6.3]
  
plt.plot(Year, Unemployment_Rate, color='red', marker='o')
plt.title('Unemployment Rate Vs Year', fontsize=14)
plt.xlabel('Year', fontsize=14)
plt.ylabel('Unemployment Rate', fontsize=14)
plt.grid(True)
plt.show()


#biểu đồ hình tròn của danh sách sinh viên đăng ký các khóa học ngôn ngữ máy tính khác nhau
from matplotlib import pyplot as plt
import numpy as np
fig = plt.figure()
ax = fig.add_axes([0,0,1,1])
ax.axis('equal')
langs = ['C', 'C++', 'Java', 'Python', 'PHP']
students = [23,17,35,29,12]
ax.pie(students, labels = langs,autopct='%1.2f%%')
plt.show()


import matplotlib.pyplot as plt


x =[5, 7, 8, 7, 2, 17, 2, 9, 4, 11, 12, 9, 6]

y =[99, 86, 87, 88, 100, 86, 103, 87, 94, 78, 77, 85, 86]

plt.scatter(x, y, c ="blue")

# To show the plot
plt.show()


import matplotlib.pyplot as plt

# dataset-1
x1 = [89, 43, 36, 36, 95, 10, 66, 34, 38, 20]

y1 = [21, 46, 3, 35, 67, 95, 53, 72, 58, 10]

# dataset2
x2 = [26, 29, 48, 64, 6, 5, 36, 66, 72, 40]

y2 = [26, 34, 90, 33, 38, 20, 56, 2, 47, 15]

plt.scatter(x1, y1, c ="pink",linewidths = 2,marker ="s",edgecolor ="green",s = 50)
plt.scatter(x2, y2, c ="yellow",linewidths = 2,marker ="^",edgecolor ="red",s = 200)
plt.xlabel("X-axis")
plt.ylabel("Y-axis")
plt.show()


# Import the required modules
import matplotlib.pyplot as plt
import numpy as np
# Set figure size
plt.figure(figsize=(8,5))
# Create the data
countries =['Qatar','Luxembourg','Singapore','Brunei','Ireland','Norway','UAE','Kuwait']
populations = [2781682,
604245,5757499,428963,4818690,5337962,9630959,4137312]
gdp_per_capita = [130475, 106705, 100345, 79530, 78785, 74356,69382, 67000]
# scale GDP per capita income to shoot the bubbles in the graph
scaled_gdp_per_capita = np.divide(gdp_per_capita, 80)
colors = np.random.rand(8)
# Draw the scatter diagram
plt.scatter(countries, populations, s=scaled_gdp_per_capita, c=colors,
cmap="Blues",edgecolors="grey", alpha=0.5)
# Add X Label on X-axis
plt.xlabel("Countries")
# Add Y Label on X-axis
plt.ylabel("Population")
# Add title to graph
plt.title("Bubble Chart")
# rotate x label for clear visualization
plt.xticks(rotation=45)
# Show the plot
plt.show()


#pip install squarify
n = titanic.groupby('class')[['survived']].sum()
n


import seaborn as sns
import squarify 
import matplotlib.pyplot as plt
 
titanic = sns.load_dataset('titanic')
 
a = titanic.groupby('class')[['survived']].sum().index.get_level_values(0).tolist()
 
d = titanic.groupby('class')[['survived']].sum().reset_index().survived.values.tolist()
 
squarify.plot(sizes=d,label=a, alpha=.8 )
plt.axis('off')
plt.show()


#!pip install wordcloud
#!pip install pillow
#!pip install matplotlib


# Importing Libraries
import pandas as pd
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS
# Importing Dataset
df = pd.read_csv("Restaurant_Reviews.tsv", sep="	")
#Creating the text variable
text = " ".join(cat for cat in df.Review)
# Generate word cloud
word_cloud = WordCloud(width=3000, height=2000, random_state=1, background_color="salmon", colormap="Pastel1", 
collocations=False, stopwords=STOPWORDS,).generate(text)
# Display the generated Word Cloud
plt.imshow(word_cloud)
plt.axis("off")
plt.show()


import numpy as np
import matplotlib.pyplot as plt

# data from United Nations World Population Prospects (Revision 2019)
# https://population.un.org/wpp/, license: CC BY 3.0 IGO
year = [1950, 1960, 1970, 1980, 1990, 2000, 2010, 2018]
population_by_continent = {
    'africa': [228, 284, 365, 477, 631, 814, 1044, 1275],
    'americas': [340, 425, 519, 619, 727, 840, 943, 1006],
    'asia': [1394, 1686, 2120, 2625, 3202, 3714, 4169, 4560],
    'europe': [220, 253, 276, 295, 310, 303, 294, 293],
    'oceania': [12, 15, 19, 22, 26, 31, 36, 39],
}

fig, ax = plt.subplots()
ax.stackplot(year, population_by_continent.values(),
             labels=population_by_continent.keys(), alpha=0.8)
ax.legend(loc='upper left')
ax.set_title('World population')
ax.set_xlabel('Year')
ax.set_ylabel('Number of people (millions)')

plt.show()


# Fixing random state for reproducibility
np.random.seed(19680801)


def gaussian_mixture(x, n=5):
    """Return a random mixture of *n* Gaussians, evaluated at positions *x*."""
    def add_random_gaussian(a):
        amplitude = 1 / (.1 + np.random.random())
        dx = x[-1] - x[0]
        x0 = (2 * np.random.random() - .5) * dx
        z = 10 / (.1 + np.random.random()) / dx
        a += amplitude * np.exp(-(z * (x - x0))**2)
    a = np.zeros_like(x)
    for j in range(n):
        add_random_gaussian(a)
    return a


x = np.linspace(0, 100, 101)
ys = [gaussian_mixture(x) for _ in range(3)]

fig, ax = plt.subplots()
ax.stackplot(x, ys, baseline='wiggle')
plt.show()


# Dendrogram thông thường
# Python program to plot the hierarchical
# clustering dendrogram using SciPy

# Import the python libraries
import numpy as np
from scipy.cluster import hierarchy
import matplotlib.pyplot as plt

# Create an array
x = np.array([100., 200., 300., 400., 500., 250.,450., 280., 450., 750.])

# Plot the hierarchical clustering as a dendrogram.
temp = hierarchy.linkage(x, 'single')
plt.figure()

dn = hierarchy.dendrogram(temp, above_threshold_color="green", color_threshold=.7)


# Dendrogram sử dụng hướng ngang
# Plot the dendrogram in horizontal orientation
# Import the python libraries
import numpy as np
from scipy.cluster import hierarchy
import matplotlib.pyplot as plt

# Create an array
x = np.array([100., 200., 300., 400., 500., 250.,450., 280., 450., 750.])

# Plot the hierarchical clustering as a dendrogram.
temp = hierarchy.linkage(x, 'single')
plt.figure()
dn = hierarchy.dendrogram(temp, above_threshold_color="green", color_threshold=.7, orientation='right')

	survived
class
First	136
Second	87
Third	119

Chương 5: Một số kỹ thuật trực quan hóa dùng trong phân tích dữ liệu¶

1. Box plots¶

2. Histograms¶

3. Heat Maps¶

4. Charts¶

a. Bar charts¶

b. Line Charts¶

c. Pie Charts¶

d. Scatter Charts¶

e. Bubble Charts¶

5. Treemaps¶

6. Word Cloud and Network diagram for Unstructured Data¶

a. Word Cloud¶

b.Network diagram¶

7. Wedge stack graphs¶

8. Streamgraphs¶

9. Dendrograms¶